© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 326
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     عرصے
    1.19
     vermelho
    1.15
    hā
    1.12
    hv
    1.11
     Saúde
    1.09
     reembolso
    1.09
    리
    1.09
    h
    1.09
    にあった
    1.05
    导弹
    1.02
    POSITIVE LOGITS
     afresh
    1.27
     anew
    1.22
    とする
    1.15
     nở
    1.15
    до
    1.13
     itibaren
    1.09
     awal
    1.05
     থেকেই
    1.05
     Helps
    1.02
    부터
    1.02
    Activations Density 1.488%

    No Known Activations